frank-default-large: swap to kingjones STRIX model on card-pinned kingjones30/ROCmFPX runtime

- runtime: charlie build-qwen38 -> kingjones30/ROCmFPX (card recipe
  build, LLAMA_BUILD_WEBUI=OFF since npm/HF-bucket provisioning fails;
  all 35 of our serving flags verified present in the tree)
- model: agentionai FAST imatrix -> kingjones777 STRIX single GGUF
  (on-host copy sha256 == HF LFS oid c6770d74...49fa verified)
- args unchanged from our validated profile (401408x2, b4096/ub512,
  t16/tb16, f16 KV, fa on, fit off); mmap stays default per card
  (PLE streams via page cache; --no-mmap = silent cgroup OOM)

scripts/serve-frank-large.sh

@@ -1,29 +1,31 @@
 #!/usr/bin/env bash
-# Serve agentionai/Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-GGUF as
-# frank-default-large via the charlie12345/ROCmFPX llama.cpp runtime
-# (build-qwen38, PR #27742 qwen4exp merged) on Dankclaw (Strix Halo
-# gfx1151, unified memory).
+# Serve kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF as
+# frank-default-large via the kingjones30/ROCmFPX llama.cpp runtime on
+# Dankclaw (Strix Halo gfx1151, unified memory).
 #
-# Runtime: charlie12345/ROCmFPX llama.cpp built at
-# /home/dank/GitPackages/ROCmFPX/build-qwen38 (HIP, gfx1151, ROCm 7.2.4).
-# The ROCmFP4 quant types (Q4_0_ROCMFP4_FAST) are hand-ported from
-# ciru-ai/ROCmFPX; upstream llama.cpp cannot load this GGUF.
+# Runtime: kingjones30/ROCmFPX (fork of charlie12345/ROCmFPX with the
+# model card's qwen4exp-on-rocmfpx patch) built at
+# /home/dank/GitPackages/kingjones-ROCmFPX/build (HIP, gfx1151,
+# ROCm 7.2.4, card recipe). The ROCmFP4 quant types plus the qwen4exp
+# architecture must be in one tree; stock llama.cpp cannot load this
+# GGUF.
 #
 # Model: Qwen3.8-Flash-Next base (qwen4exp MoE: 512 experts / 10 used,
 # 48 layers = 12 attention + 36 SSM, QSA indexer, hyper-connections, PLE
-# at layer 1) quantized Q4_0_ROCMFP4_FAST, imatrix-calibrated, 87.06 GiB.
-# The n-gram PLE table is a single per_layer_token_embd.weight tensor —
-# fully VRAM-resident, no sidecar, no --ngram-on-disk.
+# at layer 1) quantized Q4_0_ROCMFP4_STRIX, 113.47 GiB single file. The
+# 50.66 GiB PLE n-gram table stays OUT of GPU memory and streams via
+# mmap from the OS page cache — never add --no-mmap or -ot for it.
 #
 # Profile: card sampling table (temp 0.7, top_p 0.80, top_k 20, min_p 0.0,
-# presence 1.5 — non-thinking instruct) mixed with the validated
-# build-qwen38 serving profile: ctx 262144 x 1 slot, b 4096 / ub 4096,
-# t 16 / tb 16, f16 KV, fa OFF (see KNOWN CONSTRAINTS in the env file:
-# flash-attn on aborts graph build on the QSA indexer path), cont-batching,
-# prompt cache + 8 GiB cache-ram + idle-slot cache, 16 ctx checkpoints,
-# --fit off (auto-fit segfaults on qwen4exp hyper-connection config).
-# Speculative decoding is ngram-mod only; the MTP head does not load on
-# build-qwen38 (loader requires blk.0.hc_attn_norm.weight it lacks).
+# presence 1.5 — non-thinking instruct) mixed with the validated serving
+# profile: ctx 401408 x 2 slots, b 4096 / ub 512, t 16 / tb 16, f16 KV,
+# fa on (if the graph build aborts on the QSA F16 mask, see the note in
+# the env file: port scripts/patches/qwen4exp-qsa-f32-mask.patch into
+# this tree and rebuild), cont-batching, prompt cache + 8 GiB cache-ram
+# + idle-slot cache, 16 ctx checkpoints, --fit off (auto-fit segfaults
+# on qwen4exp hyper-connection config). Speculative decoding off: the
+# Flash-Next MTP heads do not load on this loader; the card ships no
+# spec flags.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
@@ -36,10 +38,10 @@ if [[ -f "$ENV_FILE" ]]; then
 fi
 
 # --- defaults (used when the env file does not set them) -------------------
-: "${LLAMA_BIN:=/home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server}"
-: "${MODEL_DIR:=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/v2}"
-: "${MODEL_FILE:=Qwen3.8-Flash-Next-ROCmFP4-FAST-imatrix-v2.gguf}"
-: "${MMPROJ_PATH:=$MODEL_DIR/../mmproj/mmproj-Qwen3.8-Flash-Next-f16.gguf}"
+: "${LLAMA_BIN:=/home/dank/GitPackages/kingjones-ROCmFPX/build/bin/llama-server}"
+: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-Flash-Next-ROCmFP4-STRIX}"
+: "${MODEL_FILE:=Qwen3.8-Flash-Next-Q4_0-ROCmFP4-STRIX.gguf}"
+: "${MMPROJ_PATH:=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/mmproj/mmproj-Qwen3.8-Flash-Next-f16.gguf}"
 : "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
 : "${CHAT_TEMPLATE_KWARGS:={}}"
 : "${ALIAS:=frank-default-large}"
@@ -122,8 +124,8 @@ if [[ -n "$SPEC_TYPE" && "$SPEC_TYPE" != "none" ]]; then
     fi
 fi
 
-# The agentionai FAST package includes the model's own vision tower (f16,
-# lossless). Pass --mmproj only when MMPROJ_PATH points at a readable file.
+# The STRIX repo ships no mmproj; this is the agentionai FAST package's
+# f16 vision tower for the same base model. Passed only when readable.
 MMPROJ_ARGS=()
 if [[ -n "${MMPROJ_PATH:-}" && -r "${MMPROJ_PATH:-}" ]]; then
     MMPROJ_ARGS=(--mmproj "$MMPROJ_PATH")